{"id":"https://openalex.org/W7167056961","doi":"https://doi.org/10.1145/3797905.3807866","title":"S2VEC: Compiler-Driven Stream Specialization for Linearized Vectorization","display_name":"S2VEC: Compiler-Driven Stream Specialization for Linearized Vectorization","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167056961","doi":"https://doi.org/10.1145/3797905.3807866"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3807866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807866","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3807866","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051849811","display_name":"Lu\u00eds Crespo","orcid":"https://orcid.org/0000-0002-1116-8859"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Lu\u00eds Crespo","raw_affiliation_strings":["INESC-ID, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-1116-8859","affiliations":[{"raw_affiliation_string":"INESC-ID, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102933880","display_name":"Ana Fernandes","orcid":"https://orcid.org/0009-0003-7613-7943"},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Ana Fernandes","raw_affiliation_strings":["Instituto de Telecomunicacoes, University of Coimbra, Coimbra, Portugal"],"raw_orcid":"https://orcid.org/0009-0003-7613-7943","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunicacoes, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I4210120471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088848663","display_name":"Gabriel Falc\u00e3o","orcid":"https://orcid.org/0000-0001-9805-6747"},"institutions":[{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Gabriel Falcao","raw_affiliation_strings":["Instituto de Telecomunicacoes, University of Coimbra, Coimbra, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-9805-6747","affiliations":[{"raw_affiliation_string":"Instituto de Telecomunicacoes, University of Coimbra, Coimbra, Portugal","institution_ids":["https://openalex.org/I4210120471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075054918","display_name":"Pedro Tom\u00e1s","orcid":"https://orcid.org/0000-0001-8083-4432"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro Tom\u00e1s","raw_affiliation_strings":["INESC-ID, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0001-8083-4432","affiliations":[{"raw_affiliation_string":"INESC-ID, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015710714","display_name":"Nuno Roma","orcid":"https://orcid.org/0000-0003-2491-4977"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Roma","raw_affiliation_strings":["INESC-ID, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-2491-4977","affiliations":[{"raw_affiliation_string":"INESC-ID, Instituto Superior T\u00e9cnico, Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058701648","display_name":"Nuno Neves","orcid":"https://orcid.org/0000-0003-0628-2259"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Neves","raw_affiliation_strings":["INESC-ID, Instituto Superior Tecnico, Universidade de Lisboa, Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-0628-2259","affiliations":[{"raw_affiliation_string":"INESC-ID, Instituto Superior Tecnico, Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84650113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"119","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8264999985694885,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8264999985694885,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.12039999663829803,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10126","display_name":"Logic, programming, and type systems","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7450000047683716},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7124999761581421},{"id":"https://openalex.org/keywords/toolchain","display_name":"Toolchain","score":0.7041000127792358},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6236000061035156},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.522599995136261},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4318999946117401},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.38609999418258667},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.3840000033378601},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8640000224113464},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7450000047683716},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7084000110626221},{"id":"https://openalex.org/C2777062904","wikidata":"https://www.wikidata.org/wiki/Q545406","display_name":"Toolchain","level":3,"score":0.7041000127792358},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.325300008058548},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.2827000021934509},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.27309998869895935},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3807866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807866","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3807866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3807866","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6222243905067444,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1999085092","https://openalex.org/W2012114780","https://openalex.org/W2013156670","https://openalex.org/W2034147186","https://openalex.org/W2040281526","https://openalex.org/W2080285119","https://openalex.org/W2118031182","https://openalex.org/W2127324789","https://openalex.org/W2142799655","https://openalex.org/W2147654959","https://openalex.org/W2147657366","https://openalex.org/W2594960649","https://openalex.org/W2613264175","https://openalex.org/W2626953429","https://openalex.org/W2899324948","https://openalex.org/W2912012512","https://openalex.org/W2953184160","https://openalex.org/W2963566954","https://openalex.org/W2976670629","https://openalex.org/W2980270412","https://openalex.org/W3013692244","https://openalex.org/W3016220765","https://openalex.org/W3016309475","https://openalex.org/W3021821229","https://openalex.org/W3033308515","https://openalex.org/W3122286897","https://openalex.org/W3150538041","https://openalex.org/W3152508978","https://openalex.org/W3157391606","https://openalex.org/W3188321821","https://openalex.org/W3191906639","https://openalex.org/W4245302940","https://openalex.org/W4280590405","https://openalex.org/W4281621335","https://openalex.org/W4285049632","https://openalex.org/W4285143823","https://openalex.org/W4285147964","https://openalex.org/W4292169167","https://openalex.org/W4311995762","https://openalex.org/W4321496225","https://openalex.org/W4327930430","https://openalex.org/W4376123125","https://openalex.org/W4390738557","https://openalex.org/W4391986270","https://openalex.org/W4399801274","https://openalex.org/W4407245202","https://openalex.org/W4407848466","https://openalex.org/W4407857640","https://openalex.org/W4414017206","https://openalex.org/W7116743250"],"related_works":[],"abstract_inverted_index":{"The":[0],"performance":[1,181],"benefits":[2,182],"of":[3,41,161,183],"vectorization":[4,120,140],"are":[5],"often":[6],"limited":[7],"by":[8],"data":[9,23,75,95],"movement,":[10],"which":[11],"remains":[12,54],"a":[13,39,91,132,152,175],"dominant":[14],"bottleneck":[15],"in":[16],"modern":[17],"processors.":[18],"To":[19],"mitigate":[20],"this":[21,57],"bottleneck,":[22],"stream-based":[24,52],"mechanisms":[25],"have":[26],"been":[27],"recently":[28],"proposed,":[29],"allowing":[30],"general-purpose":[31],"architectures":[32],"to":[33,38,77,125,146],"specialize":[34],"memory":[35,71,112,127],"accesses,":[36],"leading":[37],"reduction":[40],"load-to-use":[42],"latency":[43],"and":[44,69,104,110,121,142,171],"loop":[45],"code":[46,144],"optimizations.":[47],"However,":[48],"compiler":[49,102],"support":[50],"for":[51],"execution":[53],"limited.":[55],"Accordingly,":[56],"paper":[58],"presents":[59],"S2VEC,":[60],"an":[61,158,165],"LLVM-based":[62],"compilation":[63],"toolchain":[64],"that":[65],"automatically":[66],"extracts,":[67],"represents,":[68],"optimizes":[70],"access":[72,128],"patterns":[73],"as":[74,90],"streams":[76],"enable":[78],"stream-specialized":[79],"vector":[80],"execution.":[81],"At":[82],"its":[83,123],"core,":[84],"the":[85,98,180],"Stream-Dataflow":[86],"IR":[87],"models":[88],"computation":[89],"dataflow":[92],"over":[93,164,174],"parameterized":[94],"streams,":[96],"bridging":[97],"gap":[99],"between":[100],"conventional":[101],"infrastructures":[103],"stream-oriented":[105],"architectures.":[106],"By":[107],"transforming":[108],"complex":[109,126],"indirect":[111],"accesses":[113],"into":[114],"linearized":[115],"stream":[116,185],"representations,":[117],"S2VEC":[118,137],"simplifies":[119],"expands":[122],"applicability":[124],"patterns.":[129],"When":[130],"targeting":[131],"RISC-V":[133],"stream-vector":[134,155],"ISA":[135],"extension,":[136],"demonstrates":[138],"improved":[139],"coverage":[141],"produces":[143],"comparable":[145],"hand-optimized":[147],"implementations.":[148],"Conducted":[149],"evaluations":[150],"on":[151],"gem5-based":[153],"in-order":[154,169],"model":[156],"show":[157],"overall":[159],"speedup":[160],"5.9":[162],"\u00d7":[163,173],"equivalently":[166],"provisioned":[167],"RVV-based":[168],"core":[170],"1.5":[172],"wide":[176],"out-of-order":[177],"processor,":[178],"demonstrating":[179],"compiler-driven":[184],"specialization.":[186]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-03T00:00:00"}
